電気通信システムと管理

Machine Vision for Automatic Quality Control of Uni- directional Tape Production

Abstract

Somesh Devagekar

The  quality  of  uni-directional  tape  in  production  process  is  affected  by environmental  conditions  like  temperature  and  production  speed.  Machine  vision algorithms on the scanned images are deployed in this context to detect and classify tape damages during the manufacturing procedure. We perform a comparative study among famous feature descriptors for fault candidate generation, then propose own features for fault detection using various machine learning techniques. The empirical results   demonstrate   the   high   performance   of   the   proposed   system   and   show preference  of  random  forest  and  canny  edges  for  classifier  and  feature  generator respectively.